Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19413
    Prev
    Next
    INDEX
    Explanations

    activities related to specific processes such as poaching, caching, hacking, mining, cooking, editing, styling, and harvesting

    oai_token-act-pair · gpt-3.5-turbo

    actions or processes that involve illegal or technical activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quart
    -0.75
    oubt
    -0.65
    â̲
    -0.65
    omet
    -0.64
    lihood
    -0.64
    xus
    -0.63
    ija
    -0.62
    nerg
    -0.61
    ika
    -0.60
    rogens
    -0.60
    POSITIVE LOGITS
    HAM
    0.94
     oneself
    0.86
    redients
    0.81
     etiquette
    0.74
     Grounds
    0.73
     conventions
    0.68
     purposes
    0.66
     Practices
    0.65
     Classes
    0.65
     DRAG
    0.65
    Activations Density 0.263%

    No Known Activations